Branched session files preserve entry ids, so leaf-id equality alone let a stale /btw answer promote into a different loaded session. Capture the originating session id at /btw start and require it to match at both the controller gate and every branchFromBtw checkpoint.
Fixes#7474
- Passed the authorized leaf through the branch executor and revalidated it before rewriting history.
- Refused promotion during active turns and bounded post-prompt drains.
- Consumed unavailable branch keys while showing pending and refusal state in the panel.
Fixes#7474
Publish terminal daemon completions to the session that started the
process so idle agents can resume without polling hub status.
Persist every unacknowledged generation with a stable completion ID and
immutable snapshot. Replay the collection after reconnect or broker
recovery, and clear each event only after the owning client acknowledges
it.
Signed-off-by: Christian Stewart <christian@aperture.us>
- Added shared Python call and literal serialization utilities with multiline verbatim support.
- Standardized tool inventories to format as an OpenAI-Harmony functions namespace using TypeScript declarations.
- Updated tool normalization and rendering functions to accept options objects and default to Python-syntax examples.
- Refactored Gemini dialect rendering to leverage shared serialization functions directly.
Completed transcript entries now write through to the OS page cache on
append instead of microtask-batching, supersede in-flight atomic rewrites
with a synchronous full-body publish, and land on the live moveTo path
(source pre-rename, destination post-rename) so a software crash no longer
drops finished user/assistant/tool events. Streaming text remains durable
only at message_end; no fsync/power-loss guarantee is claimed.
Hard-coded 'scout' references reached the model even when the scout
agent was disabled via task.disabledAgents or absent from the session
spawn list. Gate every such reference on scout actually being spawnable:
the task tool description, the delegation gates, the plan-mode and
workflowz notices, the glob/grep/ast-grep guidance, and the task
specialization advisory. Prompt shape is otherwise unchanged; only
erroneous references to the unavailable subagent are dropped.
Closes#7313
A recovered artifact:// read is an ordinary read result, so the next shake
pass elides it into a new artifact, indefinitely. Extends the 5f9558d17a
spill exemption to shake; the dead-end rescue gets a dedicated config
instead of falling through to AGGRESSIVE. Manual /shake unchanged.
xd:// devices dispatch through the write tool, so a read-only call such
as an lsp navigation matched PREWALK_ACTION_TOOLS and armed the one-way
model hand-off while still reasoning about code shape.
dispatchXdevTool now records the wrapped tool's approval tier on the
XdevDispatch, and the prewalk coordinator only treats a device write as
an implementation action at write/exec tier. Direct edit/write are
unchanged.
Fixes#7312
- Make over-context models selectable in the model picker by graying them instead of disabling them.
- Trigger automatic session compaction with the current model prior to switching when an over-context model is chosen.
- Prevent xdev state allocation and tool mounting in sessions lacking a write tool.
- Expose discoverable tools top-level instead of auto-granting write transports.
Routed direct custom-message conversion through the collab steering transform so side requests and compaction see the same enveloped user turn as primary requests.
Extended the regression test to exercise convertToLlm without transformContext.
Converted user-attributed collab prompt frames to prioritized user messages only on the model-facing path, preserving guest details in persisted transcript frames.
Added regression coverage for the provider role, steering envelope, and retained guest attribution.
Fixes#7288
The move fence intentionally defers a flushSync landing in the rename window; full synchronous durability there is incompatible with orphan-avoidance for a rename-based, Windows-safe move. Document the caveat honestly instead of implying parity with the in-place rewrite path.
Refs #7270
The move fence bumped #diskEpoch, which no-oped any disk task already queued at the prior epoch (e.g. a header-only ensureOnDisk materializing rewrite), losing explicitly materialized ACP/draft sessions. Gate the append hot path on #sessionFileRelocating instead of a fresh epoch, so prior disk work still drains.
Fixes#7270
A fenced append followed by a Ctrl+C flushSync in the post-rename, pre-repoint window rewrote the full body to the old path, recreating the orphan. Sync rewrites now defer while the session file is relocating.
Fixes#7270
Rebuilt advisor runtimes with the rediscovered context files so advisor turns stop evaluating against stale AGENTS.md instructions after /reload-plugins.
Fixes#7258
Rediscovered context files from the active session cwd whenever plugin prompt sources refresh, while preserving explicitly preloaded SDK context.
Covered edited and disabled context files in the current system prompt.
Fixes#7258
- Reused the agent's explicit or inherited cache identity for ephemeral side turns.
- Forwarded the same effective key through manual and automatic native compaction.
- Added regression coverage for all three secondary request paths.
Fixes#7218
Headless hosts (print/RPC/ACP/eval/SDK) run the agent loop on the same
thread as bun:sqlite, so a lock-contention busy-wait of the interactive
5s timeout freezes the protocol loop for seconds at a time with no
liveness signal. Use a 1s busy_timeout for session-critical databases
(agent.db, history.db, stats.db) when the host is not interactive, and
let the existing asynchronous open/retry paths recover from contention.
- Reused the live Codex provider session for WebSocket-first V2 compaction.
- Fell back to SSE V2 on WebSocket transport failure before the existing V1 fallback.
- Propagated the configured WebSocket preference through manual, automatic, and advisor compaction paths.
- Added transport reuse and fallback regression coverage.
Fixes#7198
- Replaced the reactive weekly-only auto-redeem predicate with a pool-wide
planner: an expiry-salvage sweep piggybacks on the 5-minute usage
heartbeat and spends any account's reset that would otherwise expire
within codexResets.salvageHorizonHours, and the blocked-turn path scans
all stored accounts with eligibility built from the exact exhausted
5h/weekly windows (openai/codex#28525), unblocking at the latest reset
among them.
- Made the live 429's parsed unblock timestamp authoritative for the
active account (pre-block snapshots survive cache invalidation via
in-flight adoption and last-good fallback), synthesizing the candidate
when no usable report exists, and overlaying live credit counts from
the dedicated credits route since a stale /wham/usage zero is never
corrected upstream.
- Treated nothing_to_reset, credit_list_failed, and thrown consumes as
non-terminal: the episode key is released and deferred 30 minutes
instead of burying a banked credit; redeemResetCredit now spends the
soonest-expiring credit.
- Added planner unit fixtures plus integration regressions driving the
real triggers end to end, with an injectable per-session coordinator
seam and a sweep settlement handle.
- Subagents inherit the parent's eval session id, so a child's
reset: true destroyed the co-owned kernel and every sibling's
interpreter state mid-session.
- resolveOwnerScopedSessionKey now routes a reset from a non-exclusive
owner onto a deterministic per-owner fork key: the requester gets a
fresh private kernel, co-owners keep the shared one, and the fork
stays sticky for that owner until its teardown reaps it.
- Applied across Python, JavaScript, Ruby, and Julia executors; JS
contexts gained an owner registry plus disposeVmContextsByOwner,
wired into EvalRunner.disposeKernels and SDK session teardown.
- Covered by pure key-resolution contracts and an end-to-end JS test:
co-owner reset forks, shared state survives, fork is sticky, and
per-owner dispose reaps only the fork.
roboomp